Analytic Store Scoring Action Set

Provides actions for scoring using an analytic store

saveas Action

Saves an ONNX model to an analytic store.

CASL Syntax
Summary: Input and Output Tables
Parameter Descriptions

CASL Syntax

aStore.saveas <result=results> <status=rc> /

anchorBoxes={double-1 <, double-2, ...>},

inputs={{

decoded=TRUE | FALSE,

inputColorOrder="BGR" | "RGB",

inputShapeOrder="NCHW" | "NHWC",

modelColorOrder="BGR" | "RGB",

modelShapeOrder="NCHW" | "NHWC",

normFactor=double,

normMean={double-1 <, double-2, ...>},

normStd={double-1 <, double-2, ...>},

preprocess="NORMALIZE",

shape={64-bit-integer-1 <, 64-bit-integer-2, ...>},

value={double-1 <, double-2, ...>},

vars={"variable-name-1" <, "variable-name-2", ...>}

}, {...}},

intoFormattedLen=integer,

label={"string-1" <, "string-2", ...>},

maxObjects=integer,

modelType="FASTERRCNN" | "SSD" | "YOLOV2" | "YOLOV3" | "YOLOV4",

numAnchors=integer,

onnx=binary-large-object,

OrigImgDimVars={"variable-name-1" <, "variable-name-2", ...>},

outputs={{

label={"string-1" <, "string-2", ...>},

labelDim={64-bit-integer-1 <, 64-bit-integer-2, ...>},

name="string",

postprocess="SOFTMAX",

shape={64-bit-integer-1 <, 64-bit-integer-2, ...>}

}, {...}},

rstore={

caslib="string",

label="string",

lifetime=64-bit-integer,

memoryFormat="DVR" | "INHERIT" | "STANDARD",

name="table-name",

promote=TRUE | FALSE,

replace=TRUE | FALSE,

tableRedistUpPolicy="DEFER" | "NOREDIST" | "REBALANCE"

strides=integer | {integer-1 <, integer-2, ...>},

table={

caslib="string",

computedOnDemand=TRUE | FALSE,

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

computedVarsProgram="string",

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>},

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

groupByMode="NOSORT" | "REDISTRIBUTE",

importOptions={fileType="ANY" | "AUDIO" | "AUTO" | "BASESAS" | "CSV" | "DELIMITED" | "DOCUMENT" | "DTA" | "ESP" | "EXCEL" | "FMT" | "HDAT" | "IMAGE" | "JMP" | "LASR" | "PARQUET" | "SOUND" | "SPSS" | "VIDEO" | "XLS", fileType-specific-parameters},

name="table-name",

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

singlePass=TRUE | FALSE,

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

where="where-expression",

whereTable={

casLib="string"

dataSourceOptions={adls_noreq-parameters | bigquery-parameters | cas_noreq-parameters | clouddex-parameters | db2-parameters | dnfs-parameters | esp-parameters | fedsvr-parameters | gcs_noreq-parameters | hadoop-parameters | hana-parameters | impala-parameters | informix-parameters | jdbc-parameters | mongodb-parameters | mysql-parameters | odbc-parameters | oracle-parameters | path-parameters | postgres-parameters | redshift-parameters | s3-parameters | sapiq-parameters | sforce-parameters | singlestore_standard-parameters | snowflake-parameters | spark-parameters | spde-parameters | sqlserver-parameters | ss_noreq-parameters | teradata-parameters | vertica-parameters | yellowbrick-parameters}

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

xyscale={double-1 <, double-2, ...>}

;

indicates a required parameter

Summary: Input and Output Tables

If a row includes a subparameter, you can specify the name, caslib, and so on in the subparameter. Otherwise, you can specify the name, caslib, and so on in the parameter.

Parameters for Reading Input Tables
Parameter	Subparameter	Description
required parametertable	—	specifies an input table.

Parameters for Creating Output Tables
Parameter	Subparameter	Description
required parameterrstore	—	specifies a binary table that contains the analytic store.

Parameter Descriptions

anchorBoxes={double-1 <, double-2, ...>}

The dimensions of the anchor boxes for the model

Alias	anchorBox

* inputs={{astore_input_info-1} <, {astore_input_info-2}, ...>}

Input Information.

Alias	input

The astore_input_info value can be one or more of the following:

decoded=TRUE | FALSE

specifies that the input image is decoded

Default	FALSE

inputColorOrder="BGR" | "RGB"

The order of the colors for the input

inputShapeOrder="NCHW" | "NHWC"

The order of the dimensions form the input

modelColorOrder="BGR" | "RGB"

The order of the colors of the model

modelShapeOrder="NCHW" | "NHWC"

The order of the dimensions of the model

normFactor=double

The normalization factor for the input

normMean={double-1 <, double-2, ...>}

The normalization mean for the input

normStd={double-1 <, double-2, ...>}

The normalization standard deviation for the input

preprocess="NORMALIZE"

Preprocess method for the input

shape={64-bit-integer-1 <, 64-bit-integer-2, ...>}

Input Dimension Shape

value={double-1 <, double-2, ...>}

Input Values

Alias	values

varbinaryType="DOUBLE" | "FLOAT" | "INT16" | "INT32" | "INT64" | "INT8" | "UINT16" | "UINT32" | "UINT64" | "UINT8"

Input Varbinary Type

vars={"variable-name-1" <, "variable-name-2", ...>}

Input Variables

Alias	var

intoFormattedLen=integer

Output Into Column Formatted Length

label={"string-1" <, "string-2", ...>}

Output Label

Alias	labels

maxObjects=integer

Maximum number of objects to be detected

Default	10
Minimum value	1

modelType="FASTERRCNN" | "SSD" | "YOLOV2" | "YOLOV3" | "YOLOV4"

ONNX Model Type

numAnchors=integer

The number of anchor boxes for the model

Minimum value	1

* onnx=binary-large-object

Provides an ONNX model

OrigImgDimVars={"variable-name-1" <, "variable-name-2", ...>}

The height and width variables for the original images

outputs={{astore_output_info-1} <, {astore_output_info-2}, ...>}

Output Information.

Alias	output

The astore_output_info value can be one or more of the following:

label={"string-1" <, "string-2", ...>}

Output Label

Alias	labels

labelDim={64-bit-integer-1 <, 64-bit-integer-2, ...>}

Output Label Dimensions

Alias	labelDims

name="string"

Output Name

postprocess="SOFTMAX"

Postprocess method for the output

shape={64-bit-integer-1 <, 64-bit-integer-2, ...>}

Output Dimension Shape

* rstore={casouttable}

specifies a binary table that contains the analytic store.

Long form	rstore={name="table-name"}
Shortcut form	rstore="table-name"

The casouttable value can be one or more of the following:

caslib="string"

specifies the name of the caslib for the output table.

label="string"

specifies the descriptive label to associate with the table.

lifetime=64-bit-integer

specifies the number of seconds to keep the table in memory after it is last accessed. The table is dropped if it is not accessed for the specified number of seconds.

Default	0
Minimum value	0

memoryFormat="DVR" | "INHERIT" | "STANDARD"

specifies the memory format for the output table.

Default	INHERIT

DVR

use the duplicate value reduction memory format. This memory format can reduce the memory consumption and file size when the input data contains duplicate values.

INHERIT

use the default memory format that is set for the server. By default, the server uses the standard memory format. If an administrator sets the CAS_DEFAULT_MEMORY_FORMAT environment variable to DVR, then the DVR memory format is set as the default for the server.

STANDARD

use the standard memory format.

name="table-name"

specifies the name for the output table.

promote=TRUE | FALSE

when set to True, adds the output table with a global scope. This enables other sessions to access the table, subject to access controls. The target caslib must also have a global scope.

Default	FALSE

replace=TRUE | FALSE

when set to True, overwrites an existing table that has the same name.

Default	FALSE

tableRedistUpPolicy="DEFER" | "NOREDIST" | "REBALANCE"

Specifies the Table Redistribution Policy when the number of worker pods increases on a running CAS server.

DEFER

Defer redistribution policy selection to higher-level entity.

NOREDIST

Do not redistribute table data when the number of worker pods changes on a running CAS server.

REBALANCE

Rebalance table data when the number of worker pods changes on a running CAS server.

strides=integer | {integer-1 <, integer-2, ...>}

The STRIDES for the model

Alias	stride

* table={castable}

specifies an input table.

For more information about specifying the table parameter, see the common castable (Form 1) parameter (Appendix A: Common Parameters).

xyscale={double-1 <, double-2, ...>}

The XYSCALE for the model

saveas Action

Saves an ONNX model to an analytic store.

Lua Syntax
Summary: Input and Output Tables
Parameter Descriptions

Lua Syntax

results, info = s:aStore_saveas{

anchorBoxes={double-1 <, double-2, ...>},

inputs={{

decoded=true | false,

inputColorOrder="BGR" | "RGB",

inputShapeOrder="NCHW" | "NHWC",

modelColorOrder="BGR" | "RGB",

modelShapeOrder="NCHW" | "NHWC",

normFactor=double,

normMean={double-1 <, double-2, ...>},

normStd={double-1 <, double-2, ...>},

preprocess="NORMALIZE",

shape={64-bit-integer-1 <, 64-bit-integer-2, ...>},

value={double-1 <, double-2, ...>},

vars={"variable-name-1" <, "variable-name-2", ...>}

}, {...}},

intoFormattedLen=integer,

label={"string-1" <, "string-2", ...>},

maxObjects=integer,

modelType="FASTERRCNN" | "SSD" | "YOLOV2" | "YOLOV3" | "YOLOV4",

numAnchors=integer,

onnx=binary-large-object,

OrigImgDimVars={"variable-name-1" <, "variable-name-2", ...>},

outputs={{

label={"string-1" <, "string-2", ...>},

labelDim={64-bit-integer-1 <, 64-bit-integer-2, ...>},

name="string",

postprocess="SOFTMAX",

shape={64-bit-integer-1 <, 64-bit-integer-2, ...>}

}, {...}},

rstore={

caslib="string",

label="string",

lifetime=64-bit-integer,

memoryFormat="DVR" | "INHERIT" | "STANDARD",

name="table-name",

promote=true | false,

replace=true | false,

tableRedistUpPolicy="DEFER" | "NOREDIST" | "REBALANCE"

strides=integer | {integer-1 <, integer-2, ...>},

table={

caslib="string",

computedOnDemand=true | false,

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

computedVarsProgram="string",

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>},

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

groupByMode="NOSORT" | "REDISTRIBUTE",

name="table-name",

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

singlePass=true | false,

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

where="where-expression",

whereTable={

casLib="string"

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

xyscale={double-1 <, double-2, ...>}

}

indicates a required parameter

Summary: Input and Output Tables

If a row includes a subparameter, you can specify the name, caslib, and so on in the subparameter. Otherwise, you can specify the name, caslib, and so on in the parameter.

Parameters for Reading Input Tables
Parameter	Subparameter	Description
required parametertable	—	specifies an input table.

Parameters for Creating Output Tables
Parameter	Subparameter	Description
required parameterrstore	—	specifies a binary table that contains the analytic store.

Parameter Descriptions

anchorBoxes={double-1 <, double-2, ...>}

The dimensions of the anchor boxes for the model

Alias	anchorBox

* inputs={{astore_input_info-1} <, {astore_input_info-2}, ...>}

Input Information.

Alias	input

The astore_input_info value can be one or more of the following:

decoded=true | false

specifies that the input image is decoded

Default	false

inputColorOrder="BGR" | "RGB"

The order of the colors for the input

inputShapeOrder="NCHW" | "NHWC"

The order of the dimensions form the input

modelColorOrder="BGR" | "RGB"

The order of the colors of the model

modelShapeOrder="NCHW" | "NHWC"

The order of the dimensions of the model

normFactor=double

The normalization factor for the input

normMean={double-1 <, double-2, ...>}

The normalization mean for the input

normStd={double-1 <, double-2, ...>}

The normalization standard deviation for the input

preprocess="NORMALIZE"

Preprocess method for the input

shape={64-bit-integer-1 <, 64-bit-integer-2, ...>}

Input Dimension Shape

value={double-1 <, double-2, ...>}

Input Values

Alias	values

varbinaryType="DOUBLE" | "FLOAT" | "INT16" | "INT32" | "INT64" | "INT8" | "UINT16" | "UINT32" | "UINT64" | "UINT8"

Input Varbinary Type

vars={"variable-name-1" <, "variable-name-2", ...>}

Input Variables

Alias	var

intoFormattedLen=integer

Output Into Column Formatted Length

label={"string-1" <, "string-2", ...>}

Output Label

Alias	labels

maxObjects=integer

Maximum number of objects to be detected

Default	10
Minimum value	1

modelType="FASTERRCNN" | "SSD" | "YOLOV2" | "YOLOV3" | "YOLOV4"

ONNX Model Type

numAnchors=integer

The number of anchor boxes for the model

Minimum value	1

* onnx=binary-large-object

Provides an ONNX model

OrigImgDimVars={"variable-name-1" <, "variable-name-2", ...>}

The height and width variables for the original images

outputs={{astore_output_info-1} <, {astore_output_info-2}, ...>}

Output Information.

Alias	output

The astore_output_info value can be one or more of the following:

label={"string-1" <, "string-2", ...>}

Output Label

Alias	labels

labelDim={64-bit-integer-1 <, 64-bit-integer-2, ...>}

Output Label Dimensions

Alias	labelDims

name="string"

Output Name

postprocess="SOFTMAX"

Postprocess method for the output

shape={64-bit-integer-1 <, 64-bit-integer-2, ...>}

Output Dimension Shape

* rstore={casouttable}

specifies a binary table that contains the analytic store.

Long form	rstore={name="table-name"}
Shortcut form	rstore="table-name"

The casouttable value can be one or more of the following:

caslib="string"

specifies the name of the caslib for the output table.

label="string"

specifies the descriptive label to associate with the table.

lifetime=64-bit-integer

specifies the number of seconds to keep the table in memory after it is last accessed. The table is dropped if it is not accessed for the specified number of seconds.

Default	0
Minimum value	0

memoryFormat="DVR" | "INHERIT" | "STANDARD"

specifies the memory format for the output table.

Default	INHERIT

DVR

use the duplicate value reduction memory format. This memory format can reduce the memory consumption and file size when the input data contains duplicate values.

INHERIT

STANDARD

use the standard memory format.

name="table-name"

specifies the name for the output table.

promote=true | false

when set to True, adds the output table with a global scope. This enables other sessions to access the table, subject to access controls. The target caslib must also have a global scope.

Default	false

replace=true | false

when set to True, overwrites an existing table that has the same name.

Default	false

tableRedistUpPolicy="DEFER" | "NOREDIST" | "REBALANCE"

Specifies the Table Redistribution Policy when the number of worker pods increases on a running CAS server.

DEFER

Defer redistribution policy selection to higher-level entity.

NOREDIST

Do not redistribute table data when the number of worker pods changes on a running CAS server.

REBALANCE

Rebalance table data when the number of worker pods changes on a running CAS server.

strides=integer | {integer-1 <, integer-2, ...>}

The STRIDES for the model

Alias	stride

* table={castable}

specifies an input table.

For more information about specifying the table parameter, see the common castable (Form 1) parameter (Appendix A: Common Parameters).

xyscale={double-1 <, double-2, ...>}

The XYSCALE for the model

saveas Action

Saves an ONNX model to an analytic store.

Python Syntax
Summary: Input and Output Tables
Parameter Descriptions

Python Syntax

results=s.aStore.saveas(

anchorBoxes=[double-1 <, double-2, ...>],

inputs=[{

"decoded":True | False,

"inputColorOrder":"BGR" | "RGB",

"inputShapeOrder":"NCHW" | "NHWC",

"modelColorOrder":"BGR" | "RGB",

"modelShapeOrder":"NCHW" | "NHWC",

"normFactor":double,

"normMean":[double-1 <, double-2, ...>],

"normStd":[double-1 <, double-2, ...>],

"preprocess":"NORMALIZE",

"shape":[64-bit-integer-1 <, 64-bit-integer-2, ...>],

"value":[double-1 <, double-2, ...>],

"vars":["variable-name-1" <, "variable-name-2", ...>]

}<, {...}>],

intoFormattedLen=integer,

label=["string-1" <, "string-2", ...>],

maxObjects=integer,

modelType="FASTERRCNN" | "SSD" | "YOLOV2" | "YOLOV3" | "YOLOV4",

numAnchors=integer,

onnx=binary-large-object,

OrigImgDimVars=["variable-name-1" <, "variable-name-2", ...>],

outputs=[{

"label":["string-1" <, "string-2", ...>],

"labelDim":[64-bit-integer-1 <, 64-bit-integer-2, ...>],

"name":"string",

"postprocess":"SOFTMAX",

"shape":[64-bit-integer-1 <, 64-bit-integer-2, ...>]

}<, {...}>],

rstore={

"caslib":"string",

"label":"string",

"lifetime":64-bit-integer,

"memoryFormat":"DVR" | "INHERIT" | "STANDARD",

"name":"table-name",

"promote":True | False,

"replace":True | False,

"tableRedistUpPolicy":"DEFER" | "NOREDIST" | "REBALANCE"

strides=integer | [integer-1 <, integer-2, ...>],

table={

"caslib":"string",

"computedOnDemand":True | False,

"computedVars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

"computedVarsProgram":"string",

"dataSourceOptions":{"key-1":{any-list-or-data-type-1} <, "key-2":{any-list-or-data-type-2}, ...>},

"groupBy":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

"groupByMode":"NOSORT" | "REDISTRIBUTE",

"importOptions":{"fileType":"ANY" | "AUDIO" | "AUTO" | "BASESAS" | "CSV" | "DELIMITED" | "DOCUMENT" | "DTA" | "ESP" | "EXCEL" | "FMT" | "HDAT" | "IMAGE" | "JMP" | "LASR" | "PARQUET" | "SOUND" | "SPSS" | "VIDEO" | "XLS", fileType-specific-parameters},

"name":"table-name",

"orderBy":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

"singlePass":True | False,

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

"where":"where-expression",

"whereTable":{

"casLib":"string"

"dataSourceOptions":{adls_noreq-parameters | bigquery-parameters | cas_noreq-parameters | clouddex-parameters | db2-parameters | dnfs-parameters | esp-parameters | fedsvr-parameters | gcs_noreq-parameters | hadoop-parameters | hana-parameters | impala-parameters | informix-parameters | jdbc-parameters | mongodb-parameters | mysql-parameters | odbc-parameters | oracle-parameters | path-parameters | postgres-parameters | redshift-parameters | s3-parameters | sapiq-parameters | sforce-parameters | singlestore_standard-parameters | snowflake-parameters | spark-parameters | spde-parameters | sqlserver-parameters | ss_noreq-parameters | teradata-parameters | vertica-parameters | yellowbrick-parameters}

"name":"table-name"

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

}

xyscale=[double-1 <, double-2, ...>]

)

indicates a required parameter

Summary: Input and Output Tables

If a row includes a subparameter, you can specify the name, caslib, and so on in the subparameter. Otherwise, you can specify the name, caslib, and so on in the parameter.

Parameters for Reading Input Tables
Parameter	Subparameter	Description
required parametertable	—	specifies an input table.

Parameters for Creating Output Tables
Parameter	Subparameter	Description
required parameterrstore	—	specifies a binary table that contains the analytic store.

Parameter Descriptions

anchorBoxes=[double-1 <, double-2, ...>]

The dimensions of the anchor boxes for the model

Alias	anchorBox

* inputs=[{astore_input_info-1} <, {astore_input_info-2}, ...>]

Input Information.

Alias	input

The astore_input_info value can be one or more of the following:

"decoded":True | False

specifies that the input image is decoded

Default	False

"inputColorOrder":"BGR" | "RGB"

The order of the colors for the input

"inputShapeOrder":"NCHW" | "NHWC"

The order of the dimensions form the input

"modelColorOrder":"BGR" | "RGB"

The order of the colors of the model

"modelShapeOrder":"NCHW" | "NHWC"

The order of the dimensions of the model

"normFactor":double

The normalization factor for the input

"normMean":[double-1 <, double-2, ...>]

The normalization mean for the input

"normStd":[double-1 <, double-2, ...>]

The normalization standard deviation for the input

"preprocess":"NORMALIZE"

Preprocess method for the input

"shape":[64-bit-integer-1 <, 64-bit-integer-2, ...>]

Input Dimension Shape

"value":[double-1 <, double-2, ...>]

Input Values

Alias	values

"varbinaryType":"DOUBLE" | "FLOAT" | "INT16" | "INT32" | "INT64" | "INT8" | "UINT16" | "UINT32" | "UINT64" | "UINT8"

Input Varbinary Type

"vars":["variable-name-1" <, "variable-name-2", ...>]

Input Variables

Alias	var

intoFormattedLen=integer

Output Into Column Formatted Length

label=["string-1" <, "string-2", ...>]

Output Label

Alias	labels

maxObjects=integer

Maximum number of objects to be detected

Default	10
Minimum value	1

modelType="FASTERRCNN" | "SSD" | "YOLOV2" | "YOLOV3" | "YOLOV4"

ONNX Model Type

numAnchors=integer

The number of anchor boxes for the model

Minimum value	1

* onnx=binary-large-object

Provides an ONNX model

OrigImgDimVars=["variable-name-1" <, "variable-name-2", ...>]

The height and width variables for the original images

outputs=[{astore_output_info-1} <, {astore_output_info-2}, ...>]

Output Information.

Alias	output

The astore_output_info value can be one or more of the following:

"label":["string-1" <, "string-2", ...>]

Output Label

Alias	labels

"labelDim":[64-bit-integer-1 <, 64-bit-integer-2, ...>]

Output Label Dimensions

Alias	labelDims

"name":"string"

Output Name

"postprocess":"SOFTMAX"

Postprocess method for the output

"shape":[64-bit-integer-1 <, 64-bit-integer-2, ...>]

Output Dimension Shape

* rstore={casouttable}

specifies a binary table that contains the analytic store.

Long form	rstore={"name":"table-name"}
Shortcut form	rstore="table-name"

The casouttable value can be one or more of the following:

"caslib":"string"

specifies the name of the caslib for the output table.

"label":"string"

specifies the descriptive label to associate with the table.

"lifetime":64-bit-integer

specifies the number of seconds to keep the table in memory after it is last accessed. The table is dropped if it is not accessed for the specified number of seconds.

Default	0
Minimum value	0

"memoryFormat":"DVR" | "INHERIT" | "STANDARD"

specifies the memory format for the output table.

Default	INHERIT

DVR

use the duplicate value reduction memory format. This memory format can reduce the memory consumption and file size when the input data contains duplicate values.

INHERIT

STANDARD

use the standard memory format.

"name":"table-name"

specifies the name for the output table.

"promote":True | False

when set to True, adds the output table with a global scope. This enables other sessions to access the table, subject to access controls. The target caslib must also have a global scope.

Default	False

"replace":True | False

when set to True, overwrites an existing table that has the same name.

Default	False

"tableRedistUpPolicy":"DEFER" | "NOREDIST" | "REBALANCE"

Specifies the Table Redistribution Policy when the number of worker pods increases on a running CAS server.

DEFER

Defer redistribution policy selection to higher-level entity.

NOREDIST

Do not redistribute table data when the number of worker pods changes on a running CAS server.

REBALANCE

Rebalance table data when the number of worker pods changes on a running CAS server.

strides=integer | [integer-1 <, integer-2, ...>]

The STRIDES for the model

Alias	stride

* table={castable}

specifies an input table.

For more information about specifying the table parameter, see the common castable (Form 1) parameter (Appendix A: Common Parameters).

xyscale=[double-1 <, double-2, ...>]

The XYSCALE for the model

saveas Action

Saves an ONNX model to an analytic store.

R Syntax
Summary: Input and Output Tables
Parameter Descriptions

R Syntax

results <– cas.aStore.saveas(s,

anchorBoxes=list(double-1 <, double-2, ...>),

inputs=list( list(

decoded=TRUE | FALSE,

inputColorOrder="BGR" | "RGB",

inputShapeOrder="NCHW" | "NHWC",

modelColorOrder="BGR" | "RGB",

modelShapeOrder="NCHW" | "NHWC",

normFactor=double,

normMean=list(double-1 <, double-2, ...>),

normStd=list(double-1 <, double-2, ...>),

preprocess="NORMALIZE",

shape=list(64-bit-integer-1 <, 64-bit-integer-2, ...>),

value=list(double-1 <, double-2, ...>),

vars=list("variable-name-1" <, "variable-name-2", ...>)

) <, list(...)>),

intoFormattedLen=integer,

label=list("string-1" <, "string-2", ...>),

maxObjects=integer,

modelType="FASTERRCNN" | "SSD" | "YOLOV2" | "YOLOV3" | "YOLOV4",

numAnchors=integer,

onnx=binary-large-object,

OrigImgDimVars=list("variable-name-1" <, "variable-name-2", ...>),

outputs=list( list(

label=list("string-1" <, "string-2", ...>),

labelDim=list(64-bit-integer-1 <, 64-bit-integer-2, ...>),

name="string",

postprocess="SOFTMAX",

shape=list(64-bit-integer-1 <, 64-bit-integer-2, ...>)

) <, list(...)>),

rstore=list(

caslib="string",

label="string",

lifetime=64-bit-integer,

memoryFormat="DVR" | "INHERIT" | "STANDARD",

name="table-name",

promote=TRUE | FALSE,

replace=TRUE | FALSE,

tableRedistUpPolicy="DEFER" | "NOREDIST" | "REBALANCE"

strides=integer | list(integer-1 <, integer-2, ...>),

table=list(

caslib="string",

computedOnDemand=TRUE | FALSE,

computedVars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

computedVarsProgram="string",

dataSourceOptions=list(key-1=list(any-list-or-data-type-1) <, key-2=list(any-list-or-data-type-2), ...>),

groupBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

groupByMode="NOSORT" | "REDISTRIBUTE",

name="table-name",

orderBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

singlePass=TRUE | FALSE,

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

where="where-expression",

whereTable=list(

casLib="string"

name="table-name"

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

)

xyscale=list(double-1 <, double-2, ...>)

)

indicates a required parameter

Summary: Input and Output Tables

If a row includes a subparameter, you can specify the name, caslib, and so on in the subparameter. Otherwise, you can specify the name, caslib, and so on in the parameter.

Parameters for Reading Input Tables
Parameter	Subparameter	Description
required parametertable	—	specifies an input table.

Parameters for Creating Output Tables
Parameter	Subparameter	Description
required parameterrstore	—	specifies a binary table that contains the analytic store.

Parameter Descriptions

anchorBoxes=list(double-1 <, double-2, ...>)

The dimensions of the anchor boxes for the model

Alias	anchorBox

* inputs=list( list(astore_input_info-1) <, list(astore_input_info-2), ...>)

Input Information.

Alias	input

The astore_input_info value can be one or more of the following:

decoded=TRUE | FALSE

specifies that the input image is decoded

Default	FALSE

inputColorOrder="BGR" | "RGB"

The order of the colors for the input

inputShapeOrder="NCHW" | "NHWC"

The order of the dimensions form the input

modelColorOrder="BGR" | "RGB"

The order of the colors of the model

modelShapeOrder="NCHW" | "NHWC"

The order of the dimensions of the model

normFactor=double

The normalization factor for the input

normMean=list(double-1 <, double-2, ...>)

The normalization mean for the input

normStd=list(double-1 <, double-2, ...>)

The normalization standard deviation for the input

preprocess="NORMALIZE"

Preprocess method for the input

shape=list(64-bit-integer-1 <, 64-bit-integer-2, ...>)

Input Dimension Shape

value=list(double-1 <, double-2, ...>)

Input Values

Alias	values

varbinaryType="DOUBLE" | "FLOAT" | "INT16" | "INT32" | "INT64" | "INT8" | "UINT16" | "UINT32" | "UINT64" | "UINT8"

Input Varbinary Type

vars=list("variable-name-1" <, "variable-name-2", ...>)

Input Variables

Alias	var

intoFormattedLen=integer

Output Into Column Formatted Length

label=list("string-1" <, "string-2", ...>)

Output Label

Alias	labels

maxObjects=integer

Maximum number of objects to be detected

Default	10
Minimum value	1

modelType="FASTERRCNN" | "SSD" | "YOLOV2" | "YOLOV3" | "YOLOV4"

ONNX Model Type

numAnchors=integer

The number of anchor boxes for the model

Minimum value	1

* onnx=binary-large-object

Provides an ONNX model

OrigImgDimVars=list("variable-name-1" <, "variable-name-2", ...>)

The height and width variables for the original images

outputs=list( list(astore_output_info-1) <, list(astore_output_info-2), ...>)

Output Information.

Alias	output

The astore_output_info value can be one or more of the following:

label=list("string-1" <, "string-2", ...>)

Output Label

Alias	labels

labelDim=list(64-bit-integer-1 <, 64-bit-integer-2, ...>)

Output Label Dimensions

Alias	labelDims

name="string"

Output Name

postprocess="SOFTMAX"

Postprocess method for the output

shape=list(64-bit-integer-1 <, 64-bit-integer-2, ...>)

Output Dimension Shape

* rstore=list(casouttable)

specifies a binary table that contains the analytic store.

Long form	rstore=list(name="table-name")
Shortcut form	rstore="table-name"

The casouttable value can be one or more of the following:

caslib="string"

specifies the name of the caslib for the output table.

label="string"

specifies the descriptive label to associate with the table.

lifetime=64-bit-integer

specifies the number of seconds to keep the table in memory after it is last accessed. The table is dropped if it is not accessed for the specified number of seconds.

Default	0
Minimum value	0

memoryFormat="DVR" | "INHERIT" | "STANDARD"

specifies the memory format for the output table.

Default	INHERIT

DVR

use the duplicate value reduction memory format. This memory format can reduce the memory consumption and file size when the input data contains duplicate values.

INHERIT

STANDARD

use the standard memory format.

name="table-name"

specifies the name for the output table.

promote=TRUE | FALSE

when set to True, adds the output table with a global scope. This enables other sessions to access the table, subject to access controls. The target caslib must also have a global scope.

Default	FALSE

replace=TRUE | FALSE

when set to True, overwrites an existing table that has the same name.

Default	FALSE

tableRedistUpPolicy="DEFER" | "NOREDIST" | "REBALANCE"

Specifies the Table Redistribution Policy when the number of worker pods increases on a running CAS server.

DEFER

Defer redistribution policy selection to higher-level entity.

NOREDIST

Do not redistribute table data when the number of worker pods changes on a running CAS server.

REBALANCE

Rebalance table data when the number of worker pods changes on a running CAS server.

strides=integer | list(integer-1 <, integer-2, ...>)

The STRIDES for the model

Alias	stride

* table=list(castable)

specifies an input table.

For more information about specifying the table parameter, see the common castable (Form 1) parameter (Appendix A: Common Parameters).

xyscale=list(double-1 <, double-2, ...>)

The XYSCALE for the model

Last updated: November 23, 2025